Generate-and-Retrieve: Use Your Predictions to Improve Retrieval for Semantic Parsing
Yury Zemlyanskiy, Michiel de Jong, Joshua Ainslie, Panupong Pasupat, Peter Shaw, Linlu Qiu, Sumit Sanghai, Fei Sha
Abstract
A common recent approach to semantic parsing augments sequence-to-sequence models by retrieving and appending a set of training samples, called exemplars. The effectiveness of this recipe is limited by the ability to retrieve informative exemplars that help produce the correct parse, which is especially challenging in low-resource settings. Existing retrieval is commonly based on similarity of query and exemplar inputs. We propose GandR, a retrieval procedure that retrieves exemplars for which outputs are also similar. GandR first generates a preliminary prediction with input-based retrieval. Then, it retrieves exemplars with outputs similar to the preliminary prediction which are used to generate a final prediction. GandR sets the state of the art on multiple low-resource semantic parsing tasks.- Anthology ID:
- 2022.coling-1.438
- Volume:
- Proceedings of the 29th International Conference on Computational Linguistics
- Month:
- October
- Year:
- 2022
- Address:
- Gyeongju, Republic of Korea
- Venue:
- COLING
- SIG:
- Publisher:
- International Committee on Computational Linguistics
- Note:
- Pages:
- 4946–4951
- Language:
- URL:
- https://aclanthology.org/2022.coling-1.438
- DOI:
- Cite (ACL):
- Yury Zemlyanskiy, Michiel de Jong, Joshua Ainslie, Panupong Pasupat, Peter Shaw, Linlu Qiu, Sumit Sanghai, and Fei Sha. 2022. Generate-and-Retrieve: Use Your Predictions to Improve Retrieval for Semantic Parsing. In Proceedings of the 29th International Conference on Computational Linguistics, pages 4946–4951, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
- Cite (Informal):
- Generate-and-Retrieve: Use Your Predictions to Improve Retrieval for Semantic Parsing (Zemlyanskiy et al., COLING 2022)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/2022.coling-1.438.pdf
- Data
- TOPv2